Extracting Emotional Polarity of Words using Spin Model

Extracting Emotional Polarity of Words using Spin Model
复制标题

使用旋转模型提取单词的情感极性

DOI:
--
复制
发表时间:
2004
期刊:
--
影响因子:
--
通讯作者:
M. Okumura
M. Okumura
中科院分区:
--
文献类型:
--
作者:
Hiroya Takamura;Takashi Inui;M. Okumura

文献摘要

被引文献

相似文献

我们提出了一种方法来提取情感极性的话:可取的或不可取的。将情感极性看作电子的自旋,我们用平均场近似来计算系统的近似概率函数,而不是难以处理的实际概率函数。在给定“好”和“坏”两个种子词的情况下,该方法提取出500个情感极性,准确率约为75%。
We propose a method for extracting emotional polarities of words: desirable or undesirable. Regarding emotional polarities as spins of electrons, we use the mean field approximation to compute the approximate probability function of the system instead of the intractable actual probability function. Given only two seed words “good” and “bad”, the proposed method extracts 500 emotional polarities with about 75% precision.